Update app.py

app.py

@@ -1,146 +1,206 @@
 import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
 import torch
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+from PIL import Image
+import numpy as np
+import cv2
+from rembg import remove
+
+# Загрузка моделей
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-scribble")
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    controlnet=controlnet,
+    torch_dtype=torch.float16
+).to("cuda")
+
+def generate_background(image, prompt, negative_prompt):
+    # Удаление фона
+    image = Image.open(image).convert("RGBA")
+    output_image = remove(image)
+    
+    # Преобразование изображения объекта в контурное изображение
+    foreground = output_image.convert("L")
+    _, contour = cv2.threshold(np.array(foreground), 127, 255, cv2.THRESH_BINARY)
+    contour_image = Image.fromarray(contour)
+    
+    # Генерация фона
+    generator = torch.Generator(device="cuda").manual_seed(1024)
+    result = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        control_image=contour_image,
+        generator=generator,
+        num_inference_steps=50
+    )
+    
+    background = result.images[0].convert("RGBA")
+    
+    # Изменение размера фона до размера переднего плана
+    background = background.resize(output_image.size)
+    
+    # Наложение изображений
+    composite = Image.alpha_composite(background, output_image)
+    
+    return composite
+
+# Определение интерфейса Gradio
+iface = gr.Interface(
+    fn=generate_background,
+    inputs=[
+        gr.inputs.Image(type="file", label="Загрузите изображение"),
+        gr.inputs.Textbox(lines=2, placeholder="Введите позитивный промт", label="Позитивный промт"),
+        gr.inputs.Textbox(lines=2, placeholder="Введите негативный промт", label="Негативный промт")
+    ],
+    outputs=gr.outputs.Image(type="pil", label="Результат")
+)
+
+# Запуск интерфейса
+iface.launch()
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
+# import gradio as gr
+# import numpy as np
+# import random
+# from diffusers import DiffusionPipeline
+# import torch
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
+# device = "cuda" if torch.cuda.is_available() else "cpu"
 
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
+# if torch.cuda.is_available():
+#     torch.cuda.max_memory_allocated(device=device)
+#     pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+#     pipe.enable_xformers_memory_efficient_attention()
+#     pipe = pipe.to(device)
+# else: 
+#     pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
+#     pipe = pipe.to(device)
 
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+# MAX_SEED = np.iinfo(np.int32).max
+# MAX_IMAGE_SIZE = 1024
 
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+# def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+
+#     if randomize_seed:
+#         seed = random.randint(0, MAX_SEED)
         
-    generator = torch.Generator().manual_seed(seed)
+#     generator = torch.Generator().manual_seed(seed)
     
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
+#     image = pipe(
+#         prompt = prompt, 
+#         negative_prompt = negative_prompt,
+#         guidance_scale = guidance_scale, 
+#         num_inference_steps = num_inference_steps, 
+#         width = width, 
+#         height = height,
+#         generator = generator
+#     ).images[0] 
     
-    return image
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
-
-with gr.Blocks(css=css) as demo:
+#     return image
+
+# examples = [
+#     "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
+#     "An astronaut riding a green horse",
+#     "A delicious ceviche cheesecake slice",
+# ]
+
+# css="""
+# #col-container {
+#     margin: 0 auto;
+#     max-width: 520px;
+# }
+# """
+
+# if torch.cuda.is_available():
+#     power_device = "GPU"
+# else:
+#     power_device = "CPU"
+
+# with gr.Blocks(css=css) as demo:
     
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
+#     with gr.Column(elem_id="col-container"):
+#         gr.Markdown(f"""
+#         # Text-to-Image Gradio Template
+#         Currently running on {power_device}.
+#         """)
         
-        with gr.Row():
+#         with gr.Row():
             
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
+#             prompt = gr.Text(
+#                 label="Prompt",
+#                 show_label=False,
+#                 max_lines=1,
+#                 placeholder="Enter your prompt",
+#                 container=False,
+#             )
             
-            run_button = gr.Button("Run", scale=0)
+#             run_button = gr.Button("Run", scale=0)
         
-        result = gr.Image(label="Result", show_label=False)
+#         result = gr.Image(label="Result", show_label=False)
 
-        with gr.Accordion("Advanced Settings", open=False):
+#         with gr.Accordion("Advanced Settings", open=False):
             
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
+#             negative_prompt = gr.Text(
+#                 label="Negative prompt",
+#                 max_lines=1,
+#                 placeholder="Enter a negative prompt",
+#                 visible=False,
+#             )
             
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
+#             seed = gr.Slider(
+#                 label="Seed",
+#                 minimum=0,
+#                 maximum=MAX_SEED,
+#                 step=1,
+#                 value=0,
+#             )
             
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+#             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
             
-            with gr.Row():
+#             with gr.Row():
                 
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
+#                 width = gr.Slider(
+#                     label="Width",
+#                     minimum=256,
+#                     maximum=MAX_IMAGE_SIZE,
+#                     step=32,
+#                     value=512,
+#                 )
                 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
+#                 height = gr.Slider(
+#                     label="Height",
+#                     minimum=256,
+#                     maximum=MAX_IMAGE_SIZE,
+#                     step=32,
+#                     value=512,
+#                 )
             
-            with gr.Row():
+#             with gr.Row():
                 
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
+#                 guidance_scale = gr.Slider(
+#                     label="Guidance scale",
+#                     minimum=0.0,
+#                     maximum=10.0,
+#                     step=0.1,
+#                     value=0.0,
+#                 )
                 
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
+#                 num_inference_steps = gr.Slider(
+#                     label="Number of inference steps",
+#                     minimum=1,
+#                     maximum=12,
+#                     step=1,
+#                     value=2,
+#                 )
         
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
-        )
-
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
-    )
+#         gr.Examples(
+#             examples = examples,
+#             inputs = [prompt]
+#         )
+
+#     run_button.click(
+#         fn = infer,
+#         inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+#         outputs = [result]
+#     )
 
-demo.queue().launch()
+# demo.queue().launch()